monish gosar, AI Architect

AI Architect (Founding Team — Indilabs.ai)

I design and ship production agentic systems end-to-end, from discovery to multi-agent architecture, serving, and evaluation.

About

hey, i'm monish. i'm a forward-deployed AI engineer and data scientist who designs and ships production agentic systems end-to-end, from discovery to multi-agent architecture, serving, and evaluation.

right now i'm focused on agentic systems that actually understand the domain they operate in — purpose-built skills, grounded tool calls, and the ability to run full multi-turn analysis without losing context or making things up. My background in data science helps me ensure that every AI workflow is backed by robust, clean data.

Experience
  • Embedded with operating teams to translate ambiguous, manual workflows into agentic systems: running discovery, designing the architecture, and driving adoption into daily production use.
  • Designed a co-analyst framework that turns recurring analytical workflows into reusable skill cards: fetching live data, running domain analyses, and producing structured, decision-ready outputs.
  • Architected a multi-agent analytics platform on Azure OpenAI + OpenAI Agents SDK with schema-constrained tool calling and live data services: auditable answers in under 15 seconds, cutting reporting effort 40%.
  • Owned the LLM serving layer: token-budget management, rate limiting, latency reduction; plus a production ML inference layer (delinquency, propensity, forecasting) behind low-latency REST APIs across 21+ products.
  • Built a custom agent runtime with parallel tool execution, structured outputs, Langfuse tracing, and LLM-as-a-judge evaluation for factuality, completeness, and bias.
  • Shipped a contactless settlement product with NPV/DCF-optimized offers, propensity scoring, and an AI negotiation layer: +12% settlement acceptance.
Azure OpenAIOpenAI Agents SDKLangfuseFastAPIMachine Learning
  • Segmented 1,000+ users into 3 behavioral clusters via K-Means across 6 features for buyer profiling insights.
  • Built analytics pipeline: scraped 150K+ RERA records (Selenium, BeautifulSoup), modeled SQL database, delivered Power BI & Streamlit dashboards.
PythonSeleniumSQLPower BIStreamlit
I have made...
Interactive Tool

LLM Inference Economics Calculator

Explore batch size, context length, and cost tradeoffs based on the Reiner Pope lecture. Interactive charts and deep-dive into the economics of running frontier models at scale.

Try Calculator
Writing